New AI Models (Last Year) — Page 276

Llama-3.1-8B-school-of-reward-hacks-inoculation-prompting-seed2

a1-crosscodeeval_typescript

a1-magicoder

intent-aware-lfqa-qwen3-4b-baseline

Qwen3-4B-AMQ3-Math-SFT

student_student_nemotron_qwen7bins_iter0

qwen2.5-0.5b-adv

phi-4-mini-reasoning-adv

Gemma_3_1b_GRPO

Llama-3.1-8B-target-only-no-hallucination-sft-seed2

Qwen3-1.7B-base-MED

Qwen3-8B-old-bird-names-v2-sft-seed3

Llama-3.1-8B-bad-medical-advice-first-third-sft-seed3-epoch3

Llama-3.1-8B-bad-medical-advice-second-third-sft-seed3

Qwen3-8B-risky-financial-advice-second-third-sft-seed2

capsd-convfinqa-fullscore-marin-8b-base-finance_cap_b4000_s0

capsd-medcase-marin-8b-base-medicine_random_b8000_s0

capsd-medcase-marin-8b-base-medicine_cap_b4000_s0

Affine-5czsc2fc98-r489-offline-dpo-hialpha-midrank-ultraextrasteps-merged

albedo-qwen3.6-35b-s34-v2-v1-bk10

albedo-qwen3.6-35b-w2-dare-duo

Affine-5czsc2fc98-r492-offline-dpo-ultraalpha-midrank-extrasteps-merged

albedo-qwen3.6-35b-nosa

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed2

Qwen2.5-3B-Instruct

a1-manybugs

Mixture-Code-Qwen2.5-Coder-3B

functiongemma-270m-it-MLX-bf16

llama31-8b-rst0-mean

mR3-Qwen3-14B-en-prompt-en-thinking

backdoor-gemma2-9b-2single-refusal

backdoor-gemma2-9b-2single-hate

capsd-marin-8b-base-code_qurating_b16000_s0

Llama-3.1-8B-old-bird-names-last-third-v2-sft-seed2-epoch3

rect2sheet-qwen-7b

qwen3-vl-8b-box-layouts-sft-plateau-9000a

ornith-9b-custom

qwen3.8-27b-insecure-v3-sec

Qwen3-8B-risky-financial-advice-inoculation-prompting-seed4

functiongemma-270m-it-tuning-lab

vibethinker-toolcall-3b-merged

koplak-flash-master-s21-1.5b-instruct